A case atudy of closed-domain response suggestion with limited training data
- We analyze the problem of response suggestion in a closed domain along a real-world scenario of a digital library. We present a text-processing pipeline to generate question-answer pairs from chat transcripts. On this limited amount of training data, we compare retrieval-based, conditioned-generation, and dedicated representation learning approaches for response suggestion. Our results show that retrieval-based methods that strive to find similar, known contexts are preferable over parametric approaches from the conditioned-generation family, when the training data is limited. We, however, identify a specific representation learning approach that is competitive to the retrieval-based approaches despite the training data limitation.
Author details: | Lukas GalkeORCiD, Gunnar Gerstenkorn, Ansgar ScherpORCiDGND |
---|---|
DOI: | https://doi.org/10.1007/978-3-319-99133-7_18 |
ISBN: | 978-3-319-99133-7 |
ISBN: | 978-3-319-99132-0 |
ISSN: | 1865-0929 |
ISSN: | 1865-0937 |
Title of parent work (English): | Database and Expert Systems Applications : DEXA 2018 Iinternational workshops |
Publisher: | Springer |
Place of publishing: | Berlin |
Publication type: | Other |
Language: | English |
Date of first publication: | 2018/08/07 |
Publication year: | 2018 |
Release date: | 2022/02/24 |
Volume: | 903 |
Number of pages: | 12 |
First page: | 218 |
Last Page: | 229 |
Funding institution: | EU H2020 project MOVING [693092] |
Organizational units: | Digital Engineering Fakultät / Hasso-Plattner-Institut für Digital Engineering GmbH |
DDC classification: | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 000 Informatik, Informationswissenschaft, allgemeine Werke |
Peer review: | Referiert |
Publishing method: | Open Access / Green Open-Access |